EP3204896A1 - Training neural networks on partitioned training data - Google Patents
Training neural networks on partitioned training dataInfo
- Publication number
- EP3204896A1 EP3204896A1 EP15782192.7A EP15782192A EP3204896A1 EP 3204896 A1 EP3204896 A1 EP 3204896A1 EP 15782192 A EP15782192 A EP 15782192A EP 3204896 A1 EP3204896 A1 EP 3204896A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- training
- neural network
- partition
- partitions
- items
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
Definitions
- This specification relates to training neural networks.
- Neural networks are machine learning models that employ one or more layers of models to predict an output for a received input.
- Some neural networks include one or more hidden layers in addition to an output layer. The output of each hidden layer is used as input to the next layer in the network, i.e., the next hidden layer or the output layer.
- Each layer of the network generates an output from a received input in accordance with current values of a respective set of parameters.
- a recurrent neural network is a neural network that receives an input sequence and generates an output sequence from the input sequence.
- a recurrent neural network can use some or all of the internal state of the network from a previous time step in computing an output at a current time step.
- An example of a recurrent neural network is a long short term (LSTM) neural network that includes one or more LSTM memory blocks. Each LSTM memory block can include one or more cells that each include an input gate, a forget gate, and an output gate that allow the cell to store previous states for the cell, e.g., for use in generating a current activation or to be provided to other components of the LSTM neural network.
- LSTM long short term
- one innovative aspect of the subject matter described in this specification can be embodied in methods that include the actions of obtaining partitioned training data for the neural network, wherein the partitioned training data comprises a plurality of training items each of which is assigned to a respective one of a plurality of partitions, wherein each partition is associated with a respective difficulty level; and training the neural network on each of the partitions in a sequence from a partition associated with an easiest difficulty level to a partition associated with a hardest difficulty level, wherein, for each of the partitions, training the neural network comprises: training the neural network on a sequence of training items that includes training items selected from the training items in the partition interspersed with training items selected from the training items in all of the partitions.
- implementations of this and other aspects include corresponding systems, apparatus, and computer programs, configured to perform the actions of the methods, encoded on computer storage devices.
- a system of one or more computers can be so configured by virtue of software, firmware, hardware, or a combination of them installed on the system that in operation cause the system to perform the actions.
- One or more computer programs can be so configured by virtue of having instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions.
- Particular embodiments of the subject matter described in this specification can be implemented so as to realize one or more of the following advantages.
- the performance of the neural network when trained can be improved.
- the performance of the neural network when trained can be improved relative to training the neural network on a sequence that includes only training items from the partition or only training items selected from all of the partitions.
- FIG. 1 shows an example neural network training system.
- FIG. 2 is a flow diagram of an example process for training a neural network on partitioned training data.
- FIG. 3 is a flow diagram of an example process for training a neural network on a partition of training data.
- FIG. 1 shows an example neural network training system 100.
- the neural network training system 100 is an example of a system implemented as computer programs on one or more computers in one or more locations, in which the systems, components, and techniques described below can be implemented.
- the neural network training system 100 trains a neural network 110 on training items from a partitioned training data repository 120 to determine trained values of the parameters of the neural network 1 10 from initial values of the parameters.
- the neural network 110 can be a feedforward deep neural network, e.g., a convolutional neural network, or a recurrent neural network, e.g., a long short term (LSTM) neural network.
- LSTM long short term
- the neural network 110 can be configured to receive any kind of digital data input and to generate any kind of score or classification output based on the input.
- the neural network 110 is a recurrent neural network that is configured to receive the code of a computer program and to predict the output of the computer program.
- the output generated by the neural network 110 for a given image may be scores for each of a set of object categories, with each score representing an estimated likelihood that the image contains an image of an object belonging to the category.
- the output generated by the neural network 110 for a given Internet resource, document, or portion of a document may be a score for each of a set of topics, with each score representing an estimated likelihood that the Internet resource, document, or document portion is about the topic.
- the output generated by the neural network 110 may be a score that represents an estimated likelihood that the particular advertisement will be clicked on.
- the output generated by the neural network 110 may be a score for each of a set of content items, with each score representing an estimated likelihood that the user will respond favorably to being recommended the content item.
- the output generated by the neural network 1 10 may be a score for each of a set of pieces of text in another language, with each score representing an estimated likelihood that the piece of text in the other language is a proper translation of the input text into the other language.
- the output generated by the neural network 110 may be a score for each of a set of pieces of text, each score representing an estimated likelihood that the piece of text is the correct transcript for the utterance.
- each training item in the partitioned training data repository 120 is partitioned into multiple partitions such that each training item in the partitioned training data repository 120 is assigned to a respective one of the multiple partitions.
- each training item is an input of the type that the neural network 110 is configured to receive.
- each training input is associated with a respective known output, i.e., the output that should be generated by the neural network 110 by processing the training item.
- each training item in a given partition is a training item that has been assigned the difficulty level that is associated with the partition.
- generating an output that matches or closely approximates the known output for the training item is a more difficult task for the neural network 1 10 for a training item that has been assigned a harder difficulty level than for a training item that has been assigned a relatively easier difficulty level, e.g., because the training item that has been assigned the harder difficulty level is more complex than the training item that has been assigned the relatively easier difficulty level.
- the training items are partitioned and the difficulty levels are assigned by an external system or by a user, e.g., a system administrator.
- the neural network training system 100 partitions the training items and assigns the difficulty levels.
- the neural network training system 100 can determine a difficulty level of a given piece of code based on lengths of values, e.g., numeric values, in the code, based on levels of nesting present in the code, or on both.
- the neural network training system 100 trains the neural network 1 10 on all of the partitions in the partitioned training data repository 120 in a sequence that is ordered by increasing difficulty level, starting from the partition associated with the easiest difficulty level and ending with the partition associated with the hardest difficulty level. That is, the neural network training system 100 trains the neural network 1 10 first on the easiest partition in the sequence, then on the second partition in the sequence, then on the third partition in the sequence, and so on.
- the neural network training system 100 trains the neural network 1 10 on a sequence of training inputs that includes training inputs selected from the given partition and training inputs selected from all of the partitions. Training the neural network 1 10 on a given partition is described in more detail below with reference to FIG. 3.
- FIG. 2 is a flow diagram of an example process 200 for training a neural network on partitioned training data.
- the process 200 will be described as being performed by a system of one or more computers located in one or more locations.
- a neural network training system e.g., the neural network training system 100 of FIG. l, appropriately programmed, can perform the process 200.
- the system obtains partitioned training data for the neural network, e.g., from the partitioned training data repository 120 of FIG. 1 (step 202).
- the partitioned training data includes multiple training items, with each training item being assigned to a respective partition from a set of partitions. Additionally, each partition is associated with a respective difficulty level.
- the system trains the neural network on each of the partitions in sequence from a partition associated with the easiest difficulty level to the partition associated with the hardest difficulty level (step 204).
- the system trains the neural network on a sequence of training items that includes training items selected from the training items in the partition interspersed with training items selected from the training items in all of the partitions. Training the neural network on a given partition is described in more detail below with reference to FIG. 3.
- FIG. 3 is a flow diagram of an example process 300 for training a neural network on a partition of training data.
- the process 300 will be described as being performed by a system of one or more computers located in one or more locations.
- a neural network training system e.g., the neural network training system 100 of FIG. l, appropriately programmed, can perform the process 300.
- the system generates a sequence of training items for the partition (step 302).
- the system generates a sequence that includes training items selected from the partition and training items selected from all of the partitions.
- the sequence can include training items selected from the training items in all of the partitions interspersed at predetermined intervals in the sequence, e.g., at every fourth training item, every fifth training item, or every tenth training item, with the other training items being selected from the current partition.
- the training items selected from the current partition make up the majority of the training items in the sequence.
- the system selects the training items in the sequence that are selected from the current partition by randomly selecting a training item from the current partition. In some implementations, the system selects the training items in the sequence that are selected from all of the partitions by randomly selecting a training item from among the training items in the partitioned training data. In some other implementations, the system selects these training items by randomly selecting a partition, and then randomly selecting a training item from the training items in the randomly selected partition.
- the system trains the neural network on the training items in the sequence (step 304). That is, the system trains the neural network on the training items in the sequence in the order in which the training items appear in the sequence using conventional machine learning training techniques to adjust the values of the parameters of the neural network.
- the system can train the neural network on a given training item using a conventional stochastic gradient descent with backpropagation training technique. That is, the system can process the training item using the neural network to determine a neural network output for the training item, determine an error between the neural network output and the known output for the training item, and then use the error to adjust the values of the parameters of the neural network using a conventional stochastic gradient descent with backpropagation training technique.
- the system can train the neural network on a given training item using a conventional backpropagation through time training technique.
- the system determines that the performance of the neural network has stopped improving (step 306) and, in response, refrains from training the neural network further on the partition, i.e., even if the neural network has not yet been trained on all of the training items in the sequence (step 308).
- the system determines that the performance of the neural network has stopped improving when the change, e.g., a reduction, in an error measure between the known outputs for the training items in the sequence for the partition and the neural network outputs generated by the neural network for the training items becomes lower than a threshold value.
- the system can measure this error using any of a variety of conventional neural network training error measures. If the partition is not the last partition in the sequence of partitions, after determining that the performance of the neural network has stopped improving, the system begins training the neural network on the next partition in the sequence of partitions. If the partition is the last partition in the sequence, the system can terminate the training of the neural network. If the performance of the neural network never stops improving while training the neural network on the partition, the system trains the neural network on all of the training items in the sequence for the partition.
- the system trains the neural network on the partition until the neural network has been trained on the last training item in the sequence for the partition.
- Embodiments of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them.
- Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non transitory program carrier for execution by, or to control the operation of, data processing apparatus.
- the program instructions can be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus.
- the computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them. The computer storage medium is not, however, a propagated signal.
- data processing apparatus encompasses all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers.
- the apparatus can include special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
- the apparatus can also include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them.
- a computer program (which may also be referred to or described as a program, software, a software application, a module, a software module, a script, or code) can be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it can be deployed in any form, including as a stand alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
- a computer program may, but need not, correspond to a file in a file system.
- a program can be stored in a portion of a file that holds other programs or data, e.g., one or more scripts stored in a markup language document, in a single file dedicated to the program in question, or in multiple coordinated files, e.g., files that store one or more modules, sub programs, or portions of code.
- a computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
- an “engine,” or “software engine,” refers to a software implemented input/output system that provides an output that is different from the input.
- An engine can be an encoded block of functionality, such as a library, a platform, a software development kit ("SDK”), or an object.
- SDK software development kit
- Each engine can be implemented on any appropriate type of computing device, e.g., servers, mobile phones, tablet computers, notebook computers, music players, e-book readers, laptop or desktop computers, PDAs, smart phones, or other stationary or portable devices, that includes one or more processors and computer readable media. Additionally, two or more of the engines may be implemented on the same computing device, or on different computing devices.
- the processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output.
- the processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
- special purpose logic circuitry e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).
- Computers suitable for the execution of a computer program include, by way of example, can be based on general or special purpose microprocessors or both, or any other kind of central processing unit.
- a central processing unit will receive instructions and data from a read only memory or a random access memory or both.
- the essential elements of a computer are a central processing unit for performing or executing instructions and one or more memory devices for storing instructions and data.
- a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
- mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
- a computer need not have such devices.
- a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device, e.g., a universal serial bus (USB) flash drive, to name just a few.
- PDA personal digital assistant
- GPS Global Positioning System
- USB universal serial bus
- Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks.
- semiconductor memory devices e.g., EPROM, EEPROM, and flash memory devices
- magnetic disks e.g., internal hard disks or removable disks
- magneto optical disks e.g., CD ROM and DVD-ROM disks.
- the processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
- a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer.
- a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
- keyboard and a pointing device e.g., a mouse or a trackball
- Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input.
- a computer can interact with a user by sending documents to and receiving documents from a device that is used by the user; for example, by sending web pages to a
- Embodiments of the subject matter described in this specification can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the subject matter described in this specification, or any combination of one or more such back end, middleware, or front end components.
- the components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.
- LAN local area network
- WAN wide area network
- the computing system can include clients and servers.
- a client and server are generally remote from each other and typically interact through a communication network.
- the relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Machine Translation (AREA)
- Information Transfer Between Computers (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201462061035P | 2014-10-07 | 2014-10-07 | |
PCT/US2015/054188 WO2016057480A1 (en) | 2014-10-07 | 2015-10-06 | Training neural networks on partitioned training data |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3204896A1 true EP3204896A1 (en) | 2017-08-16 |
Family
ID=54337422
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP15782192.7A Ceased EP3204896A1 (en) | 2014-10-07 | 2015-10-06 | Training neural networks on partitioned training data |
Country Status (4)
Country | Link |
---|---|
US (1) | US10380482B2 (en) |
EP (1) | EP3204896A1 (en) |
CN (1) | CN106462801A (en) |
WO (1) | WO2016057480A1 (en) |
Families Citing this family (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016145516A1 (en) | 2015-03-13 | 2016-09-22 | Deep Genomics Incorporated | System and method for training neural networks |
US10757519B2 (en) * | 2016-02-23 | 2020-08-25 | Harman International Industries, Incorporated | Neural network-based parameter estimation of loudspeakers |
KR20180003123A (en) | 2016-06-30 | 2018-01-09 | 삼성전자주식회사 | Memory cell unit and recurrent neural network(rnn) including multiple memory cell units |
US10387769B2 (en) * | 2016-06-30 | 2019-08-20 | Samsung Electronics Co., Ltd. | Hybrid memory cell unit and recurrent neural network including hybrid memory cell units |
US10810482B2 (en) | 2016-08-30 | 2020-10-20 | Samsung Electronics Co., Ltd | System and method for residual long short term memories (LSTM) network |
EP3542319B1 (en) * | 2016-11-15 | 2023-07-26 | Google LLC | Training neural networks using a clustering loss |
US10671908B2 (en) | 2016-11-23 | 2020-06-02 | Microsoft Technology Licensing, Llc | Differential recurrent neural network |
US10241684B2 (en) * | 2017-01-12 | 2019-03-26 | Samsung Electronics Co., Ltd | System and method for higher order long short-term memory (LSTM) network |
EP3568811A1 (en) * | 2017-02-24 | 2019-11-20 | Deepmind Technologies Limited | Training machine learning models |
CN110326004B (en) * | 2017-02-24 | 2023-06-30 | 谷歌有限责任公司 | Training a strategic neural network using path consistency learning |
US10320819B2 (en) * | 2017-02-27 | 2019-06-11 | Amazon Technologies, Inc. | Intelligent security management |
CN110462638B (en) * | 2017-03-23 | 2023-08-01 | 渊慧科技有限公司 | Training neural networks using posterior sharpening |
EP3559868A1 (en) | 2017-03-24 | 2019-10-30 | Google LLC | Device placement optimization with reinforcement learning |
EP3610417A1 (en) | 2017-04-12 | 2020-02-19 | Deepmind Technologies Limited | Black-box optimization using neural networks |
EP3563302A1 (en) * | 2017-04-20 | 2019-11-06 | Google LLC | Processing sequential data using recurrent neural networks |
WO2018201151A1 (en) * | 2017-04-28 | 2018-11-01 | Google Llc | Neural network optimizer search |
DE102017215829A1 (en) * | 2017-09-07 | 2018-12-06 | Siemens Healthcare Gmbh | Method and data processing unit for determining classification data for an adaptation of an examination protocol |
EP3682379A1 (en) * | 2017-09-15 | 2020-07-22 | Google LLC | Augmenting neural networks |
CN109726808B (en) * | 2017-10-27 | 2022-12-09 | 腾讯科技(深圳)有限公司 | Neural network training method and device, storage medium and electronic device |
US11797839B2 (en) | 2017-10-27 | 2023-10-24 | Google Llc | Training neural networks using priority queues |
US10732639B2 (en) * | 2018-03-08 | 2020-08-04 | GM Global Technology Operations LLC | Method and apparatus for automatically generated curriculum sequence based reinforcement learning for autonomous vehicles |
JP6844564B2 (en) * | 2018-03-14 | 2021-03-17 | オムロン株式会社 | Inspection system, identification system, and learning data generator |
US10699698B2 (en) * | 2018-03-29 | 2020-06-30 | Tencent Technology (Shenzhen) Company Limited | Adaptive permutation invariant training with auxiliary information for monaural multi-talker speech recognition |
US10699697B2 (en) * | 2018-03-29 | 2020-06-30 | Tencent Technology (Shenzhen) Company Limited | Knowledge transfer in permutation invariant training for single-channel multi-talker speech recognition |
CN108549857B (en) * | 2018-03-30 | 2021-04-23 | 国信优易数据股份有限公司 | Event detection model training method and device and event detection method |
CN108647571B (en) * | 2018-03-30 | 2021-04-06 | 国信优易数据股份有限公司 | Video motion classification model training method and device and video motion classification method |
EP3782080A1 (en) | 2018-04-18 | 2021-02-24 | DeepMind Technologies Limited | Neural networks for scalable continual learning in domains with sequentially learned tasks |
CN108647782B (en) * | 2018-05-21 | 2021-10-19 | 清华大学 | Method and system for reducing eDRAM refreshing energy consumption in neural network chip |
CN109117786B (en) * | 2018-08-09 | 2021-11-30 | 百度在线网络技术(北京)有限公司 | Data processing method and device based on neural network model and readable storage medium |
CN109766493B (en) * | 2018-12-24 | 2022-08-02 | 哈尔滨工程大学 | Cross-domain recommendation method combining personality characteristics under neural network |
US11941867B2 (en) * | 2019-01-23 | 2024-03-26 | Google Llc | Neural network training using the soft nearest neighbor loss |
US11586943B2 (en) * | 2019-08-12 | 2023-02-21 | Micron Technology, Inc. | Storage and access of neural network inputs in automotive predictive maintenance |
US11681911B2 (en) * | 2019-10-15 | 2023-06-20 | Naver Corporation | Method and system for training neural sequence-to-sequence models by incorporating global features |
CN113255531B (en) * | 2021-05-31 | 2021-11-09 | 腾讯科技(深圳)有限公司 | Method and device for processing living body detection model, computer equipment and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6651244B1 (en) * | 1999-07-26 | 2003-11-18 | Cisco Technology, Inc. | System and method for determining program complexity |
US6456991B1 (en) * | 1999-09-01 | 2002-09-24 | Hrl Laboratories, Llc | Classification method and apparatus based on boosting and pruning of multiple classifiers |
US10579922B2 (en) * | 2014-04-08 | 2020-03-03 | Microsoft Technology Licensing, Llc | Deep learning using alternating direction method of multipliers |
US20160034812A1 (en) * | 2014-07-31 | 2016-02-04 | Qualcomm Incorporated | Long short-term memory using a spiking neural network |
-
2015
- 2015-10-06 EP EP15782192.7A patent/EP3204896A1/en not_active Ceased
- 2015-10-06 WO PCT/US2015/054188 patent/WO2016057480A1/en active Application Filing
- 2015-10-06 CN CN201580031864.2A patent/CN106462801A/en active Pending
- 2015-10-07 US US14/877,071 patent/US10380482B2/en active Active
Non-Patent Citations (2)
Title |
---|
None * |
See also references of WO2016057480A1 * |
Also Published As
Publication number | Publication date |
---|---|
CN106462801A (en) | 2017-02-22 |
WO2016057480A1 (en) | 2016-04-14 |
US20160098632A1 (en) | 2016-04-07 |
US10380482B2 (en) | 2019-08-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10380482B2 (en) | Training neural networks on partitioned training data | |
US11481631B1 (en) | Using embedding functions with a deep network | |
US11868888B1 (en) | Training a document classification neural network | |
US10650328B2 (en) | Training distilled machine learning models | |
US11087201B2 (en) | Neural architecture search using a performance prediction neural network | |
US10282662B2 (en) | Training neural networks using a prioritized experience memory | |
US10762422B2 (en) | Wide and deep machine learning models | |
US11416745B1 (en) | Adversarial training of neural networks | |
US11790233B2 (en) | Generating larger neural networks | |
US10691997B2 (en) | Augmenting neural networks to generate additional outputs | |
US10387531B1 (en) | Processing structured documents using convolutional neural networks | |
WO2017201506A1 (en) | Training neural networks using synthetic gradients | |
WO2015116909A1 (en) | Generating vector representations of documents | |
JP2019517075A (en) | Categorizing Example Inputs Using Comparison Sets | |
CN109643323B (en) | Selecting content items using reinforcement learning | |
US10657435B1 (en) | Processing inputs using recurrent neural networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20161222 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: GOOGLE LLC |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
17Q | First examination report despatched |
Effective date: 20190205 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20200703 |
|
GRAJ | Information related to disapproval of communication of intention to grant by the applicant or resumption of examination proceedings by the epo deleted |
Free format text: ORIGINAL CODE: EPIDOSDIGR1 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R003 |
|
INTC | Intention to grant announced (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED |
|
18R | Application refused |
Effective date: 20201005 |
|
P01 | Opt-out of the competence of the unified patent court (upc) registered |
Effective date: 20230519 |